Project Grant 2315396
Award Date
10/1/23
Completion Date
9/30/26
Dollars Obligated
$544K
Federal Agency
Division of Information and Intelligent Systems
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
New York, NY 10012, USA
Similar Awards
This National Science Foundation (NSF) Division of Electrical, Communications and Cyber Systems award, CFDA 47.041 Engineering, will provide $193,000 from September 1, 2024 to August 31, 2027 to New York University (NYU) to develop new theories and methodologies for safe reinforcement learning in domains such as robotics, autonomous driving, and power systems. The key products and services to be delivered under this Project Grant include: 1) Formulating safety measures as general objectives...
This $750,000 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program to Arizona State University focuses on developing foundational technologies for safe Reinforcement Learning (RL)-enabled systems. The 4-year project aims to establish theories, algorithms, and experiments for distributional RL to enable policy safety, exploration safety, and environmental safety in RL-powered applications like 6G networking,...
The National Science Foundation (NSF) awarded a $194,000 Project Grant under the Engineering program (CFDA 47.041) to Georgia Tech Research Corp to conduct research on safe reinforcement learning. The project aims to develop new approaches for training, improving, and evaluating reinforcement learning policies that are robust to distribution shift and non-stationarity, with the goal of ensuring safety in applications such as robotics, autonomous driving, and power systems. Key innovations...
The National Science Foundation (NSF) awarded a $375,000 Project Grant under the Computer and Information Science and Engineering (CISE) program to the Regents of the University of Michigan, Office of Research and Sponsored Projects, doing business as the University of Michigan. The grant, awarded on October 1, 2023, aims to develop foundational technologies for safe Reinforcement Learning (RL)-enabled systems, integrating research and education. The project focuses on three key thrusts: (1)...
This federal Project Grant award from the National Science Foundation's Engineering program (CFDA 47.041) provides $193,000 to the Trustees of Princeton University over a 3-year period starting September 1, 2024. The funding supports collaborative research on developing safe reinforcement learning techniques that can be applied in domains like robotics, autonomous driving, and power systems. The key research thrusts include: 1) training robust policies using distributionally robust approaches;...
This National Science Foundation (NSF) Project Grant, awarded under the Computer and Information Science and Engineering program (CFDA 47.070), provides $816,735 to Northeastern University to research techniques for improving the sample efficiency of reinforcement learning and imitation learning for robotic manipulation tasks. The key goals are to: 1) expand symmetric learning methods to handle imperfect symmetries; 2) explore object-factored symmetric models; 3) explore symmetric learning in...
This Project Grant award, provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, aims to develop tools to ensure the safe operation of autonomous systems employing reinforcement learning (RL) components. The $375,000 award, granted from September 1, 2024, to August 31, 2028, will fund research to (1) align RL agent norms with designer intent, (2) formally verify the resulting agent behavior, and (3) implement runtime...
This $398,856 National Science Foundation project grant supports research at Northwestern University to improve reinforcement learning algorithms. Specifically, the grant funds the development of sample-efficient and computationally-efficient algorithms for both online and offline reinforcement learning with function approximation. The researchers aim to incorporate optimistic exploration and pessimistic exploitation techniques using faithful uncertainty quantification for neural networks....
This $425,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research to develop a framework for ensuring the safety of future robotic systems. The research project, led by The Trustees of Princeton University, aims to lay the foundation for safe robot autonomy by enabling robots to continually prove the safety of their actions under a wide range of operating conditions, from complex physical...
This $375,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CFDA 47.070) Federal Grant Program aims to develop tools and processes to design provably safe autonomous systems. The key activities include: Developing inverse reinforcement learning algorithms to align an AI agent's norms with its designers' intent. 2) Systematically exploring the agent's norms to uncover unknowns. 3) Querying the agent to explain its reward...